English
Related papers

Related papers: Learning Multi-dimensional Human Preference for Te…

200 papers

Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent subjectivity of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Anne-Sofie Maerten , Juliane Verwiebe , Shyamgopal Karthik , Ameya Prabhu , Johan Wagemans , Matthias Bethge

Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual's visual preference. Current generative models are,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Sogand Salehi , Mahdi Shafiei , Teresa Yeo , Roman Bachmann , Amir Zamir

Recent advancements in human preference optimization, originally developed for Large Language Models (LLMs), have shown significant potential in improving text-to-image diffusion models. These methods aim to learn the distribution of…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Amir Saeidi , Yiran Luo , Agneet Chatterjee , Shamanthak Hegde , Bimsara Pathiraja , Yezhou Yang , Chitta Baral

Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-01 Huan Zhang , Jinhua Liang , Huy Phan , Wenwu Wang , Emmanouil Benetos

Current multiple-point based simulations implementations generate geostatistical models at the scale of the training image; there is an assumption that the categories are exclusive at smaller scales. The goal of this paper is to generate…

Applications · Statistics 2022-02-23 Saina Lajevardi , Clayton V. Deutsch

Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting…

Computation and Language · Computer Science 2025-02-10 Zhenglin Zhou , Xiaobo Xia , Fan Ma , Hehe Fan , Yi Yang , Tat-Seng Chua

Sequential recommender systems train their models based on a large amount of implicit user feedback data and may be subject to biases when users are systematically under/over-exposed to certain items. Unbiased learning based on inverse…

Information Retrieval · Computer Science 2023-03-16 Chen Xu , Jun Xu , Xu Chen , Zhenghua Dong , Ji-Rong Wen

Personalized content filtering, such as recommender systems, has become a critical infrastructure to alleviate information overload. However, these systems merely filter existing content and are constrained by its limited diversity, making…

Information Retrieval · Computer Science 2025-02-05 Yiyan Xu , Wenjie Wang , Yang Zhang , Biao Tang , Peng Yan , Fuli Feng , Xiangnan He

With the onset of large language models (LLMs), the performance of artificial intelligence (AI) models is becoming increasingly multi-dimensional. Accordingly, there have been several large, multi-dimensional evaluation frameworks put…

Human-Computer Interaction · Computer Science 2025-06-05 Sean Steinle

Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation with human judgments…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Yuiga Wada , Kanta Kaneda , Daichi Saito , Komei Sugiura

Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how prompts affect image variability in black-box diffusion-based models. We propose…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Raphael Tang , Xinyu Zhang , Lixinyu Xu , Yao Lu , Wenyan Li , Pontus Stenetorp , Jimmy Lin , Ferhan Ture

Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as…

Computation and Language · Computer Science 2025-03-04 Genta Indra Winata , David Anugraha , Lucky Susanto , Garry Kuwanto , Derry Tanti Wijaya

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Computation and Language · Computer Science 2026-04-03 Simona-Vasilica Oprea , Adela Bâra

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Computation and Language · Computer Science 2026-02-26 Ruochen Mao , Yuling Shi , Xiaodong Gu , Jiaheng Wei

Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving…

Computer Vision and Pattern Recognition · Computer Science 2021-01-25 Trung Q. Tran , Giang V. Nguyen , Daeyoung Kim

Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data structured as ``image - winner text - loser text'' triplets.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Kejia Chen , Jiawen Zhang , Jiacong Hu , Jiazhen Yang , Jian Lou , Zunlei Feng , Mingli Song

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one input prompt, two responses, and a preference label. As curating…

Computation and Language · Computer Science 2025-03-18 Jiaming Shen , Ran Xu , Yennie Jun , Zhen Qin , Tianqi Liu , Carl Yang , Yi Liang , Simon Baumgartner , Michael Bendersky

Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect…

Machine Learning · Computer Science 2025-05-20 Wenya Guo , Zhengkun Zhang , Xumeng Liu , Ying Zhang , Ziyu Lu , Haoze Zhu , Xubo Liu , Ruxue Yan

Text-to-video (T2V) generation has achieved remarkable progress in producing high-quality videos aligned with textual prompts. However, aligning synthesized videos with nuanced human preference remains challenging due to the subjective and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Qiushi Yang , Yingjie Chen , Yuan Yao , Yifang Men , Huaizhuo Liu , Miaomiao Cui

Most text-to-image customization techniques fine-tune models on a small set of \emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Taewook Kim , Wei Chen , Qiang Qiu